VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments

TL;DR

VIAssist is a system that adapts multi-modal large language models to assist visually impaired users by identifying relevant images and providing detailed, reliable answers to visual questions, improving understanding and interaction.

Contribution

The paper introduces VIAssist, a novel approach to adapt MLLMs for VI users, enabling better visual understanding and question answering despite image limitations.

Findings

VIAssist outperforms baseline with +0.21 BERTScore

VIAssist outperforms baseline with +0.31 ROUGE score

Provides detailed actions and reliable answers for VI users

Abstract

Individuals with visual impairments, encompassing both partial and total difficulties in visual perception, are referred to as visually impaired (VI) people. An estimated 2.2 billion individuals worldwide are affected by visual impairments. Recent advancements in multi-modal large language models (MLLMs) have showcased their extraordinary capabilities across various domains. It is desirable to help VI individuals with MLLMs' great capabilities of visual understanding and reasoning. However, it is challenging for VI people to use MLLMs due to the difficulties in capturing the desirable images to fulfill their daily requests. For example, the target object is not fully or partially placed in the image. This paper explores how to leverage MLLMs for VI individuals to provide visual-question answers. VIAssist can identify undesired images and provide detailed actions. Finally, VIAssist can provide reliable answers to users' queries based on the images. Our results show that VIAssist provides +0.21 and +0.31 higher BERTScore and ROUGE scores than the baseline, respectively.